* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include "dm-bio-list.h"
-#include <linux/raid/raid10.h>
-#include <linux/raid/bitmap.h>
+#include <linux/delay.h>
+#include <linux/blkdev.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "raid10.h"
+#include "bitmap.h"
/*
* RAID10 provides a combination of RAID0 and RAID1 functionality.
static void free_r10bio(r10bio_t *r10_bio)
{
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
/*
* Wake up any possible resync thread that waits for the device
static void put_buf(r10bio_t *r10_bio)
{
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
mempool_free(r10_bio, conf->r10buf_pool);
{
unsigned long flags;
mddev_t *mddev = r10_bio->mddev;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
spin_lock_irqsave(&conf->device_lock, flags);
list_add(&r10_bio->retry_list, &conf->retry_list);
*/
static inline void update_head_pos(int slot, r10bio_t *r10_bio)
{
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
conf->mirrors[r10_bio->devs[slot].devnum].head_position =
r10_bio->devs[slot].addr + (r10_bio->sectors);
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
int slot, dev;
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
slot = r10_bio->read_slot;
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
int slot, dev;
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
for (slot = 0; slot < conf->copies; slot++)
if (r10_bio->devs[slot].bio == bio)
mddev_t *mddev = q->queuedata;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
int max;
- unsigned int chunk_sectors = mddev->chunk_size >> 9;
+ unsigned int chunk_sectors = mddev->chunk_sectors;
unsigned int bio_sectors = bvm->bi_size >> 9;
max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
static void unplug_slaves(mddev_t *mddev)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i;
rcu_read_lock();
static int raid10_congested(void *data, int bits)
{
mddev_t *mddev = data;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i, ret = 0;
rcu_read_lock();
static int make_request(struct request_queue *q, struct bio * bio)
{
mddev_t *mddev = q->queuedata;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
mirror_info_t *mirror;
r10bio_t *r10_bio;
struct bio *read_bio;
static void status(struct seq_file *seq, mddev_t *mddev)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i;
if (conf->near_copies < conf->raid_disks)
- seq_printf(seq, " %dK chunks", mddev->chunk_size/1024);
+ seq_printf(seq, " %dK chunks", mddev->chunk_sectors / 2);
if (conf->near_copies > 1)
seq_printf(seq, " %d near-copies", conf->near_copies);
if (conf->far_copies > 1) {
static void error(mddev_t *mddev, mdk_rdev_t *rdev)
{
char b[BDEVNAME_SIZE];
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
/*
* If it is not operational, then we have already marked it as dead
if (!enough(conf))
return -EINVAL;
- if (rdev->raid_disk)
+ if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
if (rdev->saved_raid_disk >= 0 &&
* a one page request is never in violation.
*/
if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
- mddev->queue->max_sectors > (PAGE_SIZE>>9))
- mddev->queue->max_sectors = (PAGE_SIZE>>9);
+ queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
+ blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
p->head_position = 0;
rdev->raid_disk = mirror;
static void end_sync_read(struct bio *bio, int error)
{
r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
- conf_t *conf = mddev_to_conf(r10_bio->mddev);
+ conf_t *conf = r10_bio->mddev->private;
int i,d;
for (i=0; i<conf->copies; i++)
/* for reconstruct, we always reschedule after a read.
* for resync, only after all reads
*/
+ rdev_dec_pending(conf->mirrors[d].rdev, conf->mddev);
if (test_bit(R10BIO_IsRecover, &r10_bio->state) ||
atomic_dec_and_test(&r10_bio->remaining)) {
/* we have read all the blocks,
*/
reschedule_retry(r10_bio);
}
- rdev_dec_pending(conf->mirrors[d].rdev, conf->mddev);
}
static void end_sync_write(struct bio *bio, int error)
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
mddev_t *mddev = r10_bio->mddev;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i,d;
for (i = 0; i < conf->copies; i++)
update_head_pos(i, r10_bio);
+ rdev_dec_pending(conf->mirrors[d].rdev, mddev);
while (atomic_dec_and_test(&r10_bio->remaining)) {
if (r10_bio->master_bio == NULL) {
/* the primary of several recovery bios */
- md_done_sync(mddev, r10_bio->sectors, 1);
+ sector_t s = r10_bio->sectors;
put_buf(r10_bio);
+ md_done_sync(mddev, s, 1);
break;
} else {
r10bio_t *r10_bio2 = (r10bio_t *)r10_bio->master_bio;
r10_bio = r10_bio2;
}
}
- rdev_dec_pending(conf->mirrors[d].rdev, mddev);
}
/*
*/
static void sync_request_write(mddev_t *mddev, r10bio_t *r10_bio)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i, first;
struct bio *tbio, *fbio;
static void recovery_request_write(mddev_t *mddev, r10bio_t *r10_bio)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i, d;
struct bio *bio, *wbio;
r10bio_t *r10_bio;
struct bio *bio;
unsigned long flags;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
struct list_head *head = &conf->retry_list;
int unplug=0;
mdk_rdev_t *rdev;
spin_unlock_irqrestore(&conf->device_lock, flags);
mddev = r10_bio->mddev;
- conf = mddev_to_conf(mddev);
+ conf = mddev->private;
if (test_bit(R10BIO_IsSync, &r10_bio->state)) {
sync_request_write(mddev, r10_bio);
unplug = 1;
static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
r10bio_t *r10_bio;
struct bio *biolist = NULL, *bio;
sector_t max_sector, nr_sectors;
return 0;
skipped:
- max_sector = mddev->size << 1;
+ max_sector = mddev->dev_sectors;
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
max_sector = mddev->resync_max_sectors;
if (sector_nr >= max_sector) {
if (!go_faster && conf->nr_waiting)
msleep_interruptible(1000);
- bitmap_cond_end_sync(mddev->bitmap, sector_nr);
-
/* Again, very different code for resync and recovery.
* Both must result in an r10bio with a list of bios that
* have bi_end_io, bi_sector, bi_bdev set,
r10_bio->sector = sect;
raid10_find_phys(conf, r10_bio);
- /* Need to check if this section will still be
+
+ /* Need to check if the array will still be
* degraded
*/
- for (j=0; j<conf->copies;j++) {
- int d = r10_bio->devs[j].devnum;
- if (conf->mirrors[d].rdev == NULL ||
- test_bit(Faulty, &conf->mirrors[d].rdev->flags)) {
+ for (j=0; j<conf->raid_disks; j++)
+ if (conf->mirrors[j].rdev == NULL ||
+ test_bit(Faulty, &conf->mirrors[j].rdev->flags)) {
still_degraded = 1;
break;
}
- }
+
must_sync = bitmap_start_sync(mddev->bitmap, sect,
&sync_blocks, still_degraded);
/* resync. Schedule a read for every block at this virt offset */
int count = 0;
+ bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+
if (!bitmap_start_sync(mddev->bitmap, sector_nr,
&sync_blocks, mddev->degraded) &&
!conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
/* There is nowhere to write, so all non-sync
* drives must be failed, so try the next chunk...
*/
- {
- sector_t sec = max_sector - sector_nr;
- sectors_skipped += sec;
+ if (sector_nr + max_sync < max_sector)
+ max_sector = sector_nr + max_sync;
+
+ sectors_skipped += (max_sector - sector_nr);
chunks_skipped ++;
sector_nr = max_sector;
goto skipped;
- }
+}
+
+static sector_t
+raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+ sector_t size;
+ conf_t *conf = mddev->private;
+
+ if (!raid_disks)
+ raid_disks = mddev->raid_disks;
+ if (!sectors)
+ sectors = mddev->dev_sectors;
+
+ size = sectors >> conf->chunk_shift;
+ sector_div(size, conf->far_copies);
+ size = size * raid_disks;
+ sector_div(size, conf->near_copies);
+
+ return size << conf->chunk_shift;
}
static int run(mddev_t *mddev)
int i, disk_idx;
mirror_info_t *disk;
mdk_rdev_t *rdev;
- struct list_head *tmp;
int nc, fc, fo;
sector_t stride, size;
- if (mddev->chunk_size < PAGE_SIZE) {
+ if (mddev->chunk_sectors < (PAGE_SIZE >> 9) ||
+ !is_power_of_2(mddev->chunk_sectors)) {
printk(KERN_ERR "md/raid10: chunk size must be "
- "at least PAGE_SIZE(%ld).\n", PAGE_SIZE);
+ "at least PAGE_SIZE(%ld) and be a power of 2.\n", PAGE_SIZE);
return -EINVAL;
}
conf->far_copies = fc;
conf->copies = nc*fc;
conf->far_offset = fo;
- conf->chunk_mask = (sector_t)(mddev->chunk_size>>9)-1;
- conf->chunk_shift = ffz(~mddev->chunk_size) - 9;
- size = mddev->size >> (conf->chunk_shift-1);
+ conf->chunk_mask = mddev->chunk_sectors - 1;
+ conf->chunk_shift = ffz(~mddev->chunk_sectors);
+ size = mddev->dev_sectors >> conf->chunk_shift;
sector_div(size, fc);
size = size * conf->raid_disks;
sector_div(size, nc);
*/
stride += conf->raid_disks - 1;
sector_div(stride, conf->raid_disks);
- mddev->size = stride << (conf->chunk_shift-1);
+ mddev->dev_sectors = stride << conf->chunk_shift;
if (fo)
stride = 1;
spin_lock_init(&conf->device_lock);
mddev->queue->queue_lock = &conf->device_lock;
- rdev_for_each(rdev, tmp, mddev) {
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
disk_idx = rdev->raid_disk;
if (disk_idx >= mddev->raid_disks
|| disk_idx < 0)
* a one page request is never in violation.
*/
if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
- mddev->queue->max_sectors > (PAGE_SIZE>>9))
- mddev->queue->max_sectors = (PAGE_SIZE>>9);
+ queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
+ blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
disk->head_position = 0;
}
goto out_free_conf;
}
+ if (mddev->recovery_cp != MaxSector)
+ printk(KERN_NOTICE "raid10: %s is not clean"
+ " -- starting background reconstruction\n",
+ mdname(mddev));
printk(KERN_INFO
"raid10: raid set %s active with %d out of %d devices\n",
mdname(mddev), mddev->raid_disks - mddev->degraded,
/*
* Ok, everything is just fine now
*/
- mddev->array_sectors = size << conf->chunk_shift;
- mddev->resync_max_sectors = size << conf->chunk_shift;
+ md_set_array_sectors(mddev, raid10_size(mddev, 0, 0));
+ mddev->resync_max_sectors = raid10_size(mddev, 0, 0);
mddev->queue->unplug_fn = raid10_unplug;
mddev->queue->backing_dev_info.congested_fn = raid10_congested;
* maybe...
*/
{
- int stripe = conf->raid_disks * (mddev->chunk_size / PAGE_SIZE);
+ int stripe = conf->raid_disks *
+ ((mddev->chunk_sectors << 9) / PAGE_SIZE);
stripe /= conf->near_copies;
if (mddev->queue->backing_dev_info.ra_pages < 2* stripe)
mddev->queue->backing_dev_info.ra_pages = 2* stripe;
static int stop(mddev_t *mddev)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
+
+ raise_barrier(conf, 0);
+ lower_barrier(conf);
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
static void raid10_quiesce(mddev_t *mddev, int state)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
switch(state) {
case 1:
.spare_active = raid10_spare_active,
.sync_request = sync_request,
.quiesce = raid10_quiesce,
+ .size = raid10_size,
};
static int __init raid_init(void)